基于节点重要度的多机器人分布式巡逻策略

考虑到在多机器人巡逻任务中,待访问节点的重要程度存在差异是一种普遍现象,针对多数巡逻算法没有考虑节点重要程度的不同,导致所有节点的空闲时间趋于一致,从而造成重要节点访问频次不足、普通节点过度访问的问题,提出了一种基于节点重要度的分布式巡逻策略以优化节点访问频率、降低全局平均空闲时间。机器人计算周围节点空闲时间与重要度,在线决策目标节点,估计到达目标节点的时刻,并且将访问目标与估计到达时刻告知附近的同伴;为了避免某些节点被过度访问,在边缘节点的被访问频率低于最小访问频率时提高边缘节点的重要度,使得机器人可以尽快访问该点。最后,通过仿真分析了机器人数量、环境变化、重要度等因素对机器人完成持续巡逻任务的影响。结果表明,重要度大的节点被访问次数明显增加;在巡逻环境与机器人数量相同的前提下,该算法的异常值较少且平均空闲时间较小,多机器人持续巡逻性能表现较好。     

选煤厂设备巡检系统设计

针对传统的选煤厂设备管理方法存在漏检漏查、无专用仪器、数据处理繁琐等问题,提出了一种新型的选煤厂设备巡检系统的设计方案。在巡检线路及设备上安装相应的感应卡,巡检人员携带巡检仪到各点读卡,把代表该点的卡号和时间记录下来,同时完成规定的巡检和数据采集工作,然后进行下一点的巡检任务;巡检工作完成后将巡检仪的数据传送到监控计算机,由巡检数据综合信息管理软件进行处理,从而达到对巡检情况进行记录和考核的目的。实际应用表明,该系统运行稳定、功能实用。     

Selective Smooth Fictitious Play: An approach based on game theory for patrolling infrastructures with a multi-robot system

The multi-robot patrolling problem is defined as the activity of traversing a given environment. In this activity, a fleet of robots visits some places at irregular intervals of time for security purpose. To date, this problem has been solved with different approaches. However, the approaches that obtain the best results are unfeasible for security applications because they are centralized and deterministic. To overcome the disadvantages of previous work, this paper presents a new distributed and non-deterministic approach based on a model from game theory called Smooth Fictitious Play. To this end, the multi-robot patrolling problem is formulated by using concepts of graph theory to represent an environment. In this formulation, several normal-form games are defined at each node of the graph. This approach is validated by comparison with best suited literature approaches by using a patrolling simulator. The results for the proposed approach turn out to be better than previous literature approaches in as many as 88% of the cases of study. Moreover, the novel approach presented in this work has many advantages over other approaches of the literature such distribution, robustness, scalability, and dynamism. The achievements obtained in this work validate the potential of game theory to protect infrastructures.     

Optimal patrolling methodology of mobile robot for unknown visitors

This paper focuses on patrolling missions for monitoring visitors in an environment. A single mobile robot is used. For the robot, it is required to monitor as many visitors as possible utilizing the mobility and monitoring capabilities. A challenge in the patrolling missions is that the robot does not have information about the visitors beforehand. For the unknown visitors, the robot is required to identify the trends. For this purpose, a Bayesian learning approach is applied to this robot. The identified visitor trends allow the robot to employ patrolling strategies. This is the adaptability of the patrolling robot to the unknown visitors. In this paper, we present an optimal patrolling strategy based on a value iteration method. The robot is enabled to have an optimal policy that suggests three patrolling decisions, such as the target monitoring area, monitoring time, and patrolling path in an integrated way. Furthermore, the optimal patrolling strategy is improved from the viewpoint of exploration and exploitation of information about the unknown visitors in the environment. Through simulation experiments, we discuss the effectiveness of the patrolling strategy.     

基于物联网的机电设备综合巡检系统设计

针对目前煤矿机电设备维护过程中存在漏检、误检以及检查不够客观全面的问题,设计了一种基于物联网的机电设备综合巡检系统。该系统通过建立机电设备基础属性库,将机电设备的离线巡检与在线监测相结合,将人为经验检测的结果融于客观监测的信息进行综合判断,提高了对机电设备故障诊断的准确率。应用结果表明,该系统可为煤矿机电设备维修提供准确、可靠的依据,提高了煤矿设备管理水平。     

基于RFID手持终端的煤矿安全巡检系统的设计

针对传统的煤矿安全巡检方法采用人工巡检方式存在的问题,提出了一种基于RFID手持终端的煤矿安全巡检系统的设计方案。该方案中,巡检人员使用手持终端读自己的身份识别卡登录,然后通过安全管理服务器下载当班巡检任务和安全隐患库;巡检人员下井,按照下载的巡检任务依次到巡检地点刷地址识别卡,然后根据要求检测气体浓度,排查隐患,并进行相关记录;巡检结束,巡检人员通过安全管理服务器上传巡检的数据结果;安全管理人员对上传的数据进行统计和汇总,从而及时发现隐患,同时根据记录的时间判断巡检人员的脱班漏岗情况。实际应用表明,该系统能够有效地推进煤矿安全巡检工作的规范化和信息化,提升煤矿企业的安全管理水平。     

满足复杂要求的机器人最优巡回控制系统设计与实现

本文结合线性时序逻辑理论与模糊控制方法,设计并实现了一种满足复杂任务需求的移动机器人巡回控制系统,它既能够针对复杂时序任务进行路径规划,又能够对机器人进行模糊控制实现路径跟踪.首先,基于线性时序逻辑理论,确定能够满足复杂巡回任务需求的全局最优路径.接着,根据所获得的最优路径,采用模糊控制方法设计轨迹跟踪控制器,使其通过实时位姿反馈对机器人进行路径跟踪控制.仿真结果验证了移动机器人巡回控制系统的有效性.最后,基于E-Puck移动机器人构建了能够满足复杂任务需求的移动机器人巡回控制实验系统.基于所提出的最优巡回路径规划算法和模糊控制器设计方法,通过图像处理、数据通信、算法加载等软件模块的实现完成了满足复杂任务需求的移动机器人巡回控制.     

Cooperative multi-robot patrol with Bayesian learning

Patrolling indoor infrastructures with a team of cooperative mobile robots is a challenging task, which requires effective multi-agent coordination. Deterministic patrol circuits for multiple mobile robots have become popular due to their exceeding performance. However their predefined nature does not allow the system to react to changes in the system’s conditions or adapt to unexpected situations such as robot failures, thus requiring recovery behaviors in such cases. In this article, a probabilistic multi-robot patrolling strategy is proposed. A team of concurrent learning agents adapt their moves to the state of the system at the time, using Bayesian decision rules and distributed intelligence. When patrolling a given site, each agent evaluates the context and adopts a reward-based learning technique that influences future moves. Extensive results obtained in simulation and real world experiments in a large indoor environment show the potential of the approach, presenting superior results to several state of the art strategies.     

基于线性时序逻辑的最优巡回路径规划

基于线性时序逻辑(Linear temporal logic, LTL)的路径规划方法中, 多点巡回路径规划问题尚无有效解决方案. 为了在道路网络中实现最优巡回监测, 提出了基于LTL的最优巡回路径规划方法. 首先, 将环境建模成一个切换系统, 用LTL语言描述包含多个巡回点和障碍物的任务需求; 接着, 利用循环移位法构建能够融合任务需求和环境模型的扩展乘机自动机, 以建立路径信息完整的网络拓扑; 最后, 采用基于迪科斯彻法的最优综合算法搜索扩展乘机自动机网络上的最优路径, 从而获得能够满足复杂任务需求的最优巡回路径. 仿真结果表明, 该方法能够有效实现最优巡回路径规划.     

Fuzzy logic decision making for multi-robot security systems

The paper proposes a fuzzy logic decision making system for security robots that deals with multiple tasks with dynamically changing scene. The tasks consist of patrolling the environment, inspecting for missing items, chasing and disabling intruders, and guarding the area. The decision making considers robot limitations such as maximum floor coverage per robot and remaining robot battery energy, as well as cooperation among robots to complete the mission. Each robot agent makes its own decision based on its internal information as well as information broadcast to it by other robots about events such as intruder sighting. As a result the multi-robot security system is distributive without a central coordinator. The system has been implemented both in simulations and on actual robots and its performance has been verified under different scenarios.